Harmonious Music-driven Group Choreography with Trajectory-Controllable Diffusion
Creating group choreography from music is crucial in cultural entertainment and virtual reality, with a focus on generating harmonious movements. Despite growing interest, recent approaches often struggle with two major challenges: multi-dancer collisions and single-dancer foot sliding. To address these challenges, we propose a Trajectory-Controllable Diffusion (TCDiff) framework, which leverages non-overlapping trajectories to ensure coherent and aesthetically pleasing dance movements. To mitigate collisions, we introduce a Dance-Trajectory Navigator that generates collision-free trajectories for multiple dancers, utilizing a distance-consistency loss to maintain optimal spacing. Furthermore, to reduce foot sliding, we present a footwork adaptor that adjusts trajectory displacement between frames, supported by a relative forward-kinematic loss to further reinforce the correlation between movements and trajectories. Experiments demonstrate our method's superiority.
Authors
- Ronghui Li (ORCID: https://orcid.org/0000-0003-4850-0138)
- Jian Yang (ORCID: https://orcid.org/0000-0003-4887-3444)
- Zeping Ren
- Xiangzheng Zhou (ORCID: https://orcid.org/0009-0000-1761-2386)
- Jun Li (ORCID: https://orcid.org/0000-0002-4589-7371)
- Yuqin Dai
- Wanlu Zhu
- Jixuan Ying
Institutions
- University Town of Shenzhen (CN)
- Nanjing University of Science and Technology (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2025-04-11
- DOI
- https://doi.org/10.1609/aaai.v39i3.32268
- Citations
- 2
- Primary Topic
- Music Technology and Sound Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.86